General robot kinematics decomposition without intermediate markers

The calibration of serial manipulators with high numbers of degrees of freedom by means of machine learning is a complex and time-consuming task. With the help of a simple strategy, this complexity can be drastically reduced and the speed of the learning procedure can be increased: When the robot is...

ver descrição completa

Detalhes bibliográficos
Autores: Ulbrich, Stefan, Ruiz de Angulo García, Vicente|||0000-0002-2067-7399, Asfour, Tamim, Torras, Carme|||0000-0002-2933-398X, Dillmann, Rüdiger
Formato: artículo
Fecha de publicación:2012
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/17693
Acesso em linha:https://hdl.handle.net/2117/17693
https://dx.doi.org/10.1109/TNNLS.2012.2183886
Access Level:acceso abierto
Palavra-chave:Machine learning
learning (artificial intelligence) robot kinematics robots PARAULES AUTOR: KB-maps
Aprenentatge automàtic
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
id ES_9e2685d4d1cb4fbbcd9e54634065c86c
oai_identifier_str oai:upcommons.upc.edu:2117/17693
network_acronym_str ES
network_name_str España
repository_id_str
spelling General robot kinematics decomposition without intermediate markersUlbrich, StefanRuiz de Angulo García, Vicente|||0000-0002-2067-7399Asfour, TamimTorras, Carme|||0000-0002-2933-398XDillmann, RüdigerMachine learninglearning (artificial intelligence) robot kinematics robots PARAULES AUTOR: KB-mapsAprenentatge automàticClassificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàticThe calibration of serial manipulators with high numbers of degrees of freedom by means of machine learning is a complex and time-consuming task. With the help of a simple strategy, this complexity can be drastically reduced and the speed of the learning procedure can be increased: When the robot is virtually divided into shorter kinematic chains, these subchains can be learned separately and, hence, much more efficiently than the complete kinematics. Such decompositions, however, require either the possibility to capture the poses of all endeffectors of all subchains at the same time, or they are limited to robots that fulfill special constraints. In this work, an alternative decomposition is presented that does not suffer from these limitations. An offline training algorithm is provided in which the composite subchains are learned sequentially with dedicated movements. A second training scheme is provided to train composite chains simultaneously and online. Both schemes can be used together with many machine learning algorithms. In the simulations, an algorithm using Parameterized Self-Organizing Maps (PSOM) modified for online learning and Gaussian Mixture Models (GMM) were chosen to show the correctness of the approach. The experimental results show that, using a two-fold decomposition, the number of samples required to reach a given precisionPeer Reviewed20122012-01-0120132013-02-12journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/17693https://dx.doi.org/10.1109/TNNLS.2012.2183886reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengEuropean Commission http://dx.doi.org/10.13039/100011102 Seventh Framework Programme 270273 Robots Bootstrapped through Learning from ExperienceEuropean Commission http://dx.doi.org/10.13039/100011102 Seventh Framework Programme 247947 Gardening with a Cognitive Systemopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivs 3.0 Spainhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/176932026-05-27T15:37:01Z
dc.title.none.fl_str_mv General robot kinematics decomposition without intermediate markers
title General robot kinematics decomposition without intermediate markers
spellingShingle General robot kinematics decomposition without intermediate markers
Ulbrich, Stefan
Machine learning
learning (artificial intelligence) robot kinematics robots PARAULES AUTOR: KB-maps
Aprenentatge automàtic
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
title_short General robot kinematics decomposition without intermediate markers
title_full General robot kinematics decomposition without intermediate markers
title_fullStr General robot kinematics decomposition without intermediate markers
title_full_unstemmed General robot kinematics decomposition without intermediate markers
title_sort General robot kinematics decomposition without intermediate markers
dc.creator.none.fl_str_mv Ulbrich, Stefan
Ruiz de Angulo García, Vicente|||0000-0002-2067-7399
Asfour, Tamim
Torras, Carme|||0000-0002-2933-398X
Dillmann, Rüdiger
author Ulbrich, Stefan
author_facet Ulbrich, Stefan
Ruiz de Angulo García, Vicente|||0000-0002-2067-7399
Asfour, Tamim
Torras, Carme|||0000-0002-2933-398X
Dillmann, Rüdiger
author_role author
author2 Ruiz de Angulo García, Vicente|||0000-0002-2067-7399
Asfour, Tamim
Torras, Carme|||0000-0002-2933-398X
Dillmann, Rüdiger
author2_role author
author
author
author
dc.subject.none.fl_str_mv Machine learning
learning (artificial intelligence) robot kinematics robots PARAULES AUTOR: KB-maps
Aprenentatge automàtic
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
topic Machine learning
learning (artificial intelligence) robot kinematics robots PARAULES AUTOR: KB-maps
Aprenentatge automàtic
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
description The calibration of serial manipulators with high numbers of degrees of freedom by means of machine learning is a complex and time-consuming task. With the help of a simple strategy, this complexity can be drastically reduced and the speed of the learning procedure can be increased: When the robot is virtually divided into shorter kinematic chains, these subchains can be learned separately and, hence, much more efficiently than the complete kinematics. Such decompositions, however, require either the possibility to capture the poses of all endeffectors of all subchains at the same time, or they are limited to robots that fulfill special constraints. In this work, an alternative decomposition is presented that does not suffer from these limitations. An offline training algorithm is provided in which the composite subchains are learned sequentially with dedicated movements. A second training scheme is provided to train composite chains simultaneously and online. Both schemes can be used together with many machine learning algorithms. In the simulations, an algorithm using Parameterized Self-Organizing Maps (PSOM) modified for online learning and Gaussian Mixture Models (GMM) were chosen to show the correctness of the approach. The experimental results show that, using a two-fold decomposition, the number of samples required to reach a given precision
publishDate 2012
dc.date.none.fl_str_mv 2012
2012-01-01
2013
2013-02-12
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/17693
https://dx.doi.org/10.1109/TNNLS.2012.2183886
url https://hdl.handle.net/2117/17693
https://dx.doi.org/10.1109/TNNLS.2012.2183886
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv European Commission http://dx.doi.org/10.13039/100011102 Seventh Framework Programme 270273 Robots Bootstrapped through Learning from Experience
European Commission http://dx.doi.org/10.13039/100011102 Seventh Framework Programme 247947 Gardening with a Cognitive System
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivs 3.0 Spain
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivs 3.0 Spain
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869414802604949504
score 15,198674

Registos relacionados